Gemini Live 2.5 Flash Native Audio API Pricing
As of October 10, 2026, Gemini Live 2.5 Flash Native Audio costs $0.50 per 1M input tokens and $2.00 per 1M output tokens on Google Vertex AI. It has a 131,072-token context window and returns up to 65,536 tokens per response.
vertex_ai/gemini-live-2.5-flash-native-audio.- Input
- $0.50 / 1M tokens
- Output
- $2.00 / 1M tokens
- Context window
- 131,072 tokens
- Max output
- 65,536 tokens
- Providers
- 1
- Added to LiteLLM
- August 27, 2026
Gemini Live 2.5 Flash Native Audio pricing by provider
1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Context |
|---|---|---|---|---|
| Google Vertex AI | vertex_ai/gemini-live-2.5-flash-native-audio | $0.50 | $2.00 | 128K |
Other Gemini Live 2.5 Flash Native Audio prices on Google Vertex AI
| Audio input | $3.00 per 1M tokens |
| Audio output | $12.00 per 1M tokens |
| Web search | $35.00 per 1K searches |
What Gemini Live 2.5 Flash Native Audio costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Google Vertex AI | $2.00 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Google Vertex AI | $5.40 |
Gemini Live 2.5 Flash Native Audio features
Input: text, image, audio, video. Output: text, audio.
- Function calling
- Parallel tool calls
- Structured output
- Image input
- PDF input
- Audio input
- Audio output
- Prompt caching
- Web search
Use Gemini Live 2.5 Flash Native Audio with LiteLLM
Call Gemini Live 2.5 Flash Native Audio through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/realtime. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="vertex_ai/gemini-live-2.5-flash-native-audio",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: gemini-live-2.5-flash-native-audio
litellm_params:
model: vertex_ai/gemini-live-2.5-flash-native-audio
vertex_project: os.environ/VERTEX_PROJECT
vertex_location: os.environ/VERTEX_LOCATIONcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "gemini-live-2.5-flash-native-audio",
"messages": [{"role": "user", "content": "Hello!"}]
}'Gemini Live 2.5 Flash Native Audio FAQ
How much does Gemini Live 2.5 Flash Native Audio cost?
Gemini Live 2.5 Flash Native Audio costs $0.50 per 1M input tokens and $2.00 per 1M output tokens on Google Vertex AI.
What is the context window of Gemini Live 2.5 Flash Native Audio?
Gemini Live 2.5 Flash Native Audio has a 131,072-token context window and returns up to 65,536 tokens per response.
Which providers offer Gemini Live 2.5 Flash Native Audio?
Gemini Live 2.5 Flash Native Audio is available from Google Vertex AI through LiteLLM, using the model name vertex_ai/gemini-live-2.5-flash-native-audio.
How do I call Gemini Live 2.5 Flash Native Audio with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="vertex_ai/gemini-live-2.5-flash-native-audio", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/realtime from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does Gemini Live 2.5 Flash Native Audio support?
Gemini Live 2.5 Flash Native Audio supports function calling, parallel tool calls, image input, audio input, audio output and web search. It does not support structured output, PDF input and prompt caching.
When did LiteLLM add Gemini Live 2.5 Flash Native Audio?
Gemini Live 2.5 Flash Native Audio was added to LiteLLM's model price file on August 27, 2026.
Is Gemini Live 2.5 Flash Native Audio being deprecated?
Google Vertex AI lists a deprecation date of December 13, 2026 for vertex_ai/gemini-live-2.5-flash-native-audio.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
LiteLLM docs: Google Vertex AI.
Provider pages: Google Vertex AI.